© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 14038
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes and applications

    oai_token-act-pair · gpt-3.5-turbo

    elements related to processes, management, and environmental factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooked
    -0.69
     Dollars
    -0.67
    etheless
    -0.65
     sidx
    -0.65
    soDeliveryDate
    -0.64
    pire
    -0.63
     Marketable
    -0.63
     Pants
    -0.62
    0000000
    -0.62
    quished
    -0.62
    POSITIVE LOGITS
     management
    1.40
     creation
    1.39
     retrieval
    1.39
     manipulation
    1.37
     acquisition
    1.35
    creation
    1.31
     extraction
    1.30
     preparation
    1.30
     preservation
    1.29
    finding
    1.27
    Activations Density 0.671%

    No Known Activations